L2M: AI-assisted marine ecosystem monitoring

This project aims to turn raw underwater video into decision-ready science. Our software automatically detects, classifies, and counts marine species, then delivers results in a simple web dashboard with linked video clips, maps, and exportable reports. Instead of annotating from scratch, ecologists just review and correct AI suggestions—cutting review time by more than half. Built for real-world conditions, it flags unknown species, handles uncertain IDs with genus- or family-level counts, and works across different cameras, habitats, and seasons. Backed by peer-reviewed methods and expert-annotated Atlantic datasets, and led by my PhD research in partnership with Fisheries and Oceans Canada, this solution combines scientific rigor with deployable AI. Whether regulators, operators, or researchers, our users can ask: “How many cod were at Site 12 in June?” and get traceable, audit-ready answers in minutes instead of months.

Faculty Supervisor:

Christopher Whidden

Student:

Partner:

Springboard Atlantic Inc.

Discipline:

Computer science

Sector:

Artificial Intelligence; Ocean Tech; Technology

University:

Dalhousie University

Program: